iDEA: Drexel E-repository and Archives >
Drexel Academic Community >
College of Information Science and Technology >
Faculty Research and Publications (IST) >
Case-based reasoning for cash flow forecasting using fuzzy retrieval
Please use this identifier to cite or link to this item:
|Title: ||Case-based reasoning for cash flow forecasting using fuzzy retrieval|
|Authors: ||Weber-Lee, Rosina|
Barcia, Ricardo Miranda
Khator, Suresh K.
|Issue Date: ||1995 |
|Publisher: ||Springer Verlag|
|Citation: ||Case-Based Reasoning Research and Development: Proceedings of the 1st International Conference on Case-Based Reasoning, ICCBR-95: pp. 510-519.|
|Abstract: ||Case-Based Reasoning systems use successful past experiences to
solve similar problems simulating human approach. Although CBR
systems differ from one another, the basic procedure starts with a
retrieval method that searches for similar cases in comparison to an input
problem. This method must retrieve the case most similar to the input
problem resulting the best match. An adaptation phase checks whether
the solution of the best match can be readily used to solve the input
problem. When the input problem is solved, the adapted solution can be
added to the memory of cases.
The nature of the cases and their retrieval methods may vary.
Section 4 describes Fuzzy Set Theory and how its mechanisms are used
to improve the evaluation of similarities on retrieval. The present system
uses a fuzzy retrieval and it aims to forecast accounts in cash flows.
The Case-Based Reasoner is implemented under an Intelligent
Hybrid System (IHS) in a unit called Case-Based Forecasting Unit
(CBFU). Before detailing the unit, let us briefly describe its environment
(Weber-Lee et al. 1995). The IHS consists of units performing different
functions. The project of IHS is object-oriented although some units are
still in prototype phase and their modeling into the object-oriented
paradigm is being studied. Some of the units of the Intelligent Hybrid
System are: Firm, the unit that embodies every function of the company;
Case-Based Forecasting Unit, the CBFU is discussed below separately;
Database, it keeps the operations and feeds CBFU with all actual values;
Interface, there is the interface to input operations and the interface of
decision support; Expert System, the expert system unit is the one that
manages the IHS’s interface and asks cash flow forecasts for CBFU. The
Expert System1 (ES) designed for IHS manages the interface with the
user and its knowledge representation is also object-oriented.
Hence, the CBFU is a CBR application that forecasts cash flows
in the IHS that is the Working Capital decision support system. This
paper proposes a fuzzy retrieval to improve the CBR application. Next
section presents the importance of cash flow forecasting and how it is
linked to the WC management. Then, the following section shows the
1 See Expert Systems: Principles and Programming, (Giarratano, 1994).
advantages on the use of CBR as the forecasting technique. Section 3
describes the CBFU unit and its components. Lastly, section 4 presents
the fuzzy retrieval, how it is implemented and the meaning of some of the
Fuzzy Set Theory concepts applied.|
|Appears in Collections:||Faculty Research and Publications (IST)|
Items in iDEA are protected by copyright, with all rights reserved, unless otherwise indicated.